arXiv AI
Robo-Saber: Generating and Simulating Virtual Reality Players
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Computer Vision
Sep 23
GameDirector: Decoupling Gameplay Logic from Rendering for Player-Configurable Game World Models
arXiv:2609.25652v1 Announce Type: new Abstract: Recent game world models support realistic visual simulation and interactive gameplay based on player inputs. However, they typically learn environment...
arXiv AI
Jun 10
A Survey of Robotic Navigation and Manipulation with Physics Simulators in the Era of Embodied AI
arXiv:2505. 01458v2 Announce Type: replace-cross Abstract: Navigation and manipulation are core capabilities in Embodied AI, but training agents to perform them directly in the real world is costly, time-consuming, and unsafe.
arXiv AI
Jun 2
Coding Agent Is Good As World Simulator
arXiv:2605. 14398v2 Announce Type: replace Abstract: World models have emerged as a powerful paradigm for building interactive simulation environments, with recent video-based approaches demonstrating impressive progress in generating visually plausible dynamics.
arXiv Machine Learning
Oct 8
Kuration SDK: Addressing the Virtual2Real Gap via Data Curation
The paper introduces Kuration SDK, a toolkit for curating raw gameplay data to address the Virtual2Real gap in action‑conditioned world models. It demonstrates that conventional metrics like FVD, LPIPS, and JEDi do not reliably predict playability, using CounterStrike data to show divergent model performance despite similar scores. By providing curation strategies and diagnostic tools, the SDK helps uncover root causes of the gap and accelerate the creation of sample‑efficient training datasets.
arXiv AI
Jul 21
PhysAgent: Reflective Agentic Physics Control for Physically Plausible Video Generation
arXiv:2607. 16355v1 Announce Type: cross Abstract: Recent advances in physics-grounded video generation leverage physics simulation as a physical prior to guide video synthesis toward physically plausible outcomes.
arXiv Computer Vision
3d ago
DeVI: Physics-based Dexterous Human-Object Interaction via Synthetic Video Imitation
DeVI (Dexterous Video Imitation) is a framework that learns physics‑based character control for dexterous human‑object interaction by imitating text‑conditioned synthetic videos. It introduces hybrid imitation targets that combine reconstructed 3D human motion with tracked 2D object trajectories, avoiding explicit 3D object motion reconstruction. Visual HOI Alignment further refines the human reference to match both the generated video and the initial 3D object configuration, improving reconstruction quality and imitation success.